© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98722
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģåı£æ°Ķ
    -0.25
     Brothers
    -0.25
    rvine
    -0.24
    AEA
    -0.23
     Kis
    -0.23
    !"↵↵
    -0.23
    ï¼ģãĢį
    -0.23
     mâ
    -0.23
     braz
    -0.23
     Sar
    -0.22
    POSITIVE LOGITS
    æĸĩä¸Ń
    0.31
    ollen
    0.31
    éĩıåĮĸ
    0.28
    alsa
    0.27
    olic
    0.27
     undone
    0.27
    (Resource
    0.26
    utable
    0.25
    irt
    0.25
     bre
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.